user: codelion

3046 karma | created 18 years ago

recent submissions

From HashHop to Memory-Augmented Language Models (huggingface.co)

2 pts|1 month ago|discuss

The Optimal Architecture for Small Language Models (huggingface.co)

1 pts|2 months ago|discuss

Enhancing LLMs with LoRA – Standardized Recipes for Capability Enhancement (huggingface.co)

3 pts|2 months ago|discuss

OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution (algorithmicsuperintelligence.ai)

53 pts|2 months ago|9 comments

Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement (huggingface.co)

1 pts|2 months ago|discuss

The 1B Token Challenge: Finding the Perfect Pre-Training Mix (huggingface.co)

6 pts|3 months ago|discuss

The 1B Token Challenge: Finding the Perfect Pre-Training Mix (huggingface.co)

3 pts|3 months ago|discuss

(no title)

3 months ago|discuss

(no title)

6 months ago|discuss

Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training (huggingface.co)

2 pts|6 months ago|1 comment

(no title)

6 months ago|discuss

Internal Coherence Maximization(ICM): Label-Free Unsupervised Training Framework (github.com)

1 pts|6 months ago|discuss

Unsupervised Model Improvement via Internal Coherence Maximization (huggingface.co)

1 pts|7 months ago|discuss

Show HN: PTS Library – Analyze LLM reasoning through "thought anchors"

2 pts|7 months ago|discuss

Automated Discovery of High-Performance GPU Kernels with OpenEvolve (huggingface.co)

4 pts|8 months ago|discuss

Adaptive Classifier: Dynamic Text Classification with Continuous Learning (huggingface.co)

1 pts|8 months ago|discuss

Show HN: DeepThink Plugin – Bring Gemini 2.5's parallel reasoning to open models

4 pts|8 months ago|discuss

Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques (arxiv.org)

1 pts|8 months ago|discuss

(no title)

9 months ago|discuss

(no title)

9 months ago|discuss